[regression drm/noveau] suspend to ram -> BOOM: exception RIP: drm_calc_vbltimestamp_from_scanoutpos+335

[Mike Galbraith]

Greetings,

I met $subject in master-rt post drm merge, but taking the config
(attached) to virgin v4.12-10624-g9967468c0a10, it's reproducible.

      KERNEL: vmlinux-4.12.0.g9967468-preempt.gz
    DUMPFILE: vmcore
        CPUS: 8
        DATE: Tue Jul 11 18:55:28 2017
      UPTIME: 00:02:03
LOAD AVERAGE: 3.43, 1.39, 0.52
       TASKS: 467
    NODENAME: homer
     RELEASE: 4.12.0.g9967468-preempt
     VERSION: #155 SMP PREEMPT Tue Jul 11 18:18:11 CEST 2017
     MACHINE: x86_64  (3591 Mhz)
      MEMORY: 16 GB
       PANIC: "BUG: unable to handle kernel paging request at ffffffffa022990f"
         PID: 4658
     COMMAND: "kworker/u16:26"
        TASK: ffff8803c6068f80  [THREAD_INFO: ffff8803c6068f80]
         CPU: 7
       STATE: TASK_RUNNING (PANIC)

crash> bt
PID: 4658   TASK: ffff8803c6068f80  CPU: 7   COMMAND: "kworker/u16:26"
 #0 [ffffc900039f76a0] machine_kexec at ffffffff810481fc
 #1 [ffffc900039f76f0] __crash_kexec at ffffffff81109e3a
 #2 [ffffc900039f77b0] crash_kexec at ffffffff8110adc9
 #3 [ffffc900039f77c8] oops_end at ffffffff8101d059
 #4 [ffffc900039f77e8] no_context at ffffffff81055ce5
 #5 [ffffc900039f7838] do_page_fault at ffffffff81056c5b
 #6 [ffffc900039f7860] page_fault at ffffffff81690a88
    [exception RIP: report_bug+93]
    RIP: ffffffff8167227d  RSP: ffffc900039f7918  RFLAGS: 00010002
    RAX: ffffffffa0229905  RBX: ffffffffa020af0f  RCX: 0000000000000001
    RDX: 0000000000000907  RSI: ffffffffa020af11  RDI: ffffffffffff98f6
    RBP: ffffc900039f7a58   R8: 0000000000000001   R9: 00000000000003fc
    R10: ffffffff81a01906  R11: ffff8803f84711f8  R12: ffffffffa02231fb
    R13: 0000000000000260  R14: 0000000000000004  R15: 0000000000000006
    ORIG_RAX: ffffffffffffffff  CS: 0010  SS: 0018
 #7 [ffffc900039f7910] report_bug at ffffffff81672248
 #8 [ffffc900039f7938] fixup_bug at ffffffff8101af85
 #9 [ffffc900039f7950] do_trap at ffffffff8101b0d9
#10 [ffffc900039f79a0] do_error_trap at ffffffff8101b190
#11 [ffffc900039f7a50] invalid_op at ffffffff8169063e
    [exception RIP: drm_calc_vbltimestamp_from_scanoutpos+335]
    RIP: ffffffffa020af0f  RSP: ffffc900039f7b00  RFLAGS: 00010086
    RAX: ffffffffa04fa100  RBX: ffff8803f9550800  RCX: 0000000000000001
    RDX: ffffffffa0228a58  RSI: 0000000000000001  RDI: ffffffffa022321b
    RBP: ffffc900039f7b80   R8: 0000000000000000   R9: ffffffffa020adc0
    R10: ffffffffa048a1b0  R11: ffff8803f84711f8  R12: 0000000000000001
    R13: ffff8803f8471000  R14: ffffc900039f7b94  R15: ffffc900039f7bd0
    ORIG_RAX: ffffffffffffffff  CS: 0010  SS: 0018
#12 [ffffc900039f7b18] gf119_head_vblank_put at ffffffffa04422f9 [nouveau]
#13 [ffffc900039f7b88] drm_get_last_vbltimestamp at ffffffffa020ad91 [drm]
#14 [ffffc900039f7ba8] drm_update_vblank_count at ffffffffa020b3e1 [drm]
#15 [ffffc900039f7c10] drm_vblank_disable_and_save at ffffffffa020bbe9 [drm]
#16 [ffffc900039f7c40] drm_crtc_vblank_off at ffffffffa020c3c0 [drm]
#17 [ffffc900039f7cb0] nouveau_display_fini at ffffffffa048a4d6 [nouveau]
#18 [ffffc900039f7ce0] nouveau_display_suspend at ffffffffa048ac4f [nouveau]
#19 [ffffc900039f7d00] nouveau_do_suspend at ffffffffa047e5ec [nouveau]
#20 [ffffc900039f7d38] nouveau_pmops_suspend at ffffffffa047e77d [nouveau]
#21 [ffffc900039f7d50] pci_pm_suspend at ffffffff813b1ff0
#22 [ffffc900039f7d80] dpm_run_callback at ffffffff814c4dbd
#23 [ffffc900039f7db8] __device_suspend at ffffffff814c5a61
#24 [ffffc900039f7e30] async_suspend at ffffffff814c5cfa
#25 [ffffc900039f7e48] async_run_entry_fn at ffffffff81091683
#26 [ffffc900039f7e70] process_one_work at ffffffff810882bc
#27 [ffffc900039f7eb0] worker_thread at ffffffff8108854a
#28 [ffffc900039f7f10] kthread at ffffffff8108e387
#29 [ffffc900039f7f50] ret_from_fork at ffffffff8168fa85
crash> gdb list *drm_calc_vbltimestamp_from_scanoutpos+335
0xffffffffa020af0f is in drm_calc_vbltimestamp_from_scanoutpos (drivers/gpu/drm/drm_vblank.c:608).
603             /* If mode timing undefined, just return as no-op:
604              * Happens during initial modesetting of a crtc.
605              */
606             if (mode->crtc_clock == 0) {
607                     DRM_DEBUG("crtc %u: Noop due to uninitialized mode.\n", pipe);
608                     WARN_ON_ONCE(drm_drv_uses_atomic_modeset(dev));
609     
610                     return false;
611             }
612     
crash> gdb list *report_bug+93
0xffffffff8167227d is in report_bug (lib/bug.c:177).
172                                     return BUG_TRAP_TYPE_WARN;
173     
174                             /*
175                              * Since this is the only store, concurrency is not an issue.
176                              */
177                             bug->flags |= BUGFLAG_DONE;
178                     }
179             }
180     
181             if (warning) {
crash>

Attachment: config.xz
Description: application/xz